CN111428063B - Image feature association processing method and system based on geographic space position division - Google Patents
Image feature association processing method and system based on geographic space position division Download PDFInfo
- Publication number
- CN111428063B CN111428063B CN202010243925.4A CN202010243925A CN111428063B CN 111428063 B CN111428063 B CN 111428063B CN 202010243925 A CN202010243925 A CN 202010243925A CN 111428063 B CN111428063 B CN 111428063B
- Authority
- CN
- China
- Prior art keywords
- vector
- sample
- feature
- image
- map table
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 17
- 239000013598 vector Substances 0.000 claims abstract description 183
- 238000000034 method Methods 0.000 claims abstract description 29
- 239000003550 marker Substances 0.000 claims abstract description 25
- 238000012545 processing Methods 0.000 claims description 16
- 238000013507 mapping Methods 0.000 claims description 12
- 238000013500 data storage Methods 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 8
- 238000000638 solvent extraction Methods 0.000 claims description 5
- 230000000007 visual effect Effects 0.000 description 5
- 238000000605 extraction Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/55—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5846—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using extracted text
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/587—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Software Systems (AREA)
- Processing Or Creating Images (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides an image feature association processing method and system based on geographic space position division, wherein the method comprises the following steps: establishing a first hash map table according to the geographic position of each video stream camera, extracting image text characteristics and sample vector characteristics of a target image sample, storing the image text characteristics and preset associated marker bits into a preset database, and storing the sample vector characteristics and the associated marker bits into a vector characteristic list; acquiring vector features and the affiliated geographical position of a target image to be searched, and searching the first hash map table according to the affiliated geographical position to acquire a corresponding vector feature list; and calculating the similarity between each sample vector feature and the vector feature in the vector feature list, determining K sample vector features with the highest similarity and associated marker bits thereof, and acquiring K image text features. The technical scheme provided by the invention can solve the problems of low speed and low precision of the existing image information storage and retrieval method.
Description
Technical Field
The invention relates to the technical field of image feature processing, in particular to an image feature association processing method and system based on geographic space position division.
Background
Along with the development of AI at present, the image intelligent processing technology has been applied in various fields, in the field of image intelligent analysis technology, there are two general ways for storing image information, one is image text label storage, and the other is image visual feature storage, and the image text label storage is that is, text information of an object in an image (such as a picture with the object being a pedestrian, the text information being gender, coat color, etc.) is acquired and stored in a corresponding database, and later, the text information is acquired through database information matching, so as to realize the retrieval of the object image.
Regarding image visual feature storage, namely, firstly, feature vectors (divided into integer type data and floating point type data and low-dimensional vectors such as 128-dimension and Gao Weiru-dimension and 2048-dimension feature vectors) of a target image are acquired by a feature extraction mode and stored in a database, and later, image retrieval is realized by a feature vector matching mode.
However, the method of purely using the image text labels for storage is fast, but the later retrieval effect is poor, and the wanted matching pictures cannot be searched; for some matching targets (such as pedestrian targets), the interference targets of similar vector features are more for different targets, and the accuracy of searching the images by the images is seriously affected.
Furthermore, the storage and retrieval of image text labels typically uses relational or non-relational databases; the storage of the visual features of the images can also be carried out by using relational or non-relational databases, but the search engines of the databases have very low search efficiency under the existing large-scale visual feature engines, and seriously affect the working efficiency.
In addition, in the existing image visual feature storage process, all vector features acquired in the early stage are often stored in a database (in a memory or a hard disk), and as time is accumulated, the data volume in the database is larger and larger, so that the data matching efficiency and accuracy in the later stage retrieval process are seriously affected, and the data processing speed of the whole system is seriously hardened.
Therefore, based on several problems, there is a need for an efficient and high-precision image information storage and retrieval method thereof.
Disclosure of Invention
The invention provides an image feature association processing method and system based on geographic space position division, and mainly aims to solve the problems of low speed and low precision of the existing image information storage and retrieval method.
In order to achieve the above object, the present invention provides an image feature association processing method based on geospatial location division, the method comprising the steps of:
a first hash map table is established in a system memory according to the geographic position of each video stream camera, wherein a vector feature list corresponding to each geographic position is arranged in the first hash map table;
extracting image text features and sample vector features of a target image sample, storing the image text features and preset associated marker bits into a preset database, and storing the sample vector features and the associated marker bits into the vector feature list; wherein the image text feature is associated with the sample vector feature through the associated marker bit;
acquiring vector features and the affiliated geographical position of a target image to be searched, and searching the first hash map table according to the affiliated geographical position to acquire a vector feature list corresponding to the affiliated geographical position;
calculating the similarity between each sample vector feature in the vector feature list and the vector feature of the target image to be searched, and determining K sample vector features with the highest similarity and associated flag bits thereof;
and searching a preset database according to the K associated flag bits with the highest similarity so as to obtain corresponding K image text features.
In another aspect, the present invention further provides an image feature association processing system based on geospatial location division, where the image feature association processing system based on geospatial location division includes:
the system comprises a table construction unit, a first hash map table, a second hash map table and a storage unit, wherein the table construction unit is used for building a first hash map table in a system memory according to the geographic positions of all video stream cameras, and a vector feature list corresponding to each geographic position is arranged in the first hash map table;
the data storage unit is used for extracting image text characteristics and sample vector characteristics of a target image sample, storing the image text characteristics and preset associated marker bits into a preset database, and storing the sample vector characteristics and the associated marker bits into the vector characteristic list; wherein the image text feature is associated with the vector feature through the associated flag bit;
the vector feature list acquisition unit is used for acquiring vector features and the affiliated geographic position of the target image to be searched, and searching the first hash map table according to the affiliated geographic position to acquire a vector feature list corresponding to the affiliated geographic position;
the similarity matching unit is used for calculating the similarity between each sample vector feature in the vector feature list and the vector feature of the target image to be searched, and determining K sample vector features with the highest similarity and associated flag bits thereof;
and the searching unit is used for searching the preset database according to the K associated flag bits so as to acquire corresponding K image text features.
According to the image feature association processing method and system based on the geographic space position division, the geographic positions of the sources (video stream cameras) of the pictures are divided, and the corresponding vector feature list is established, so that the classification and storage of the original data can be realized, the later retrieval speed can be improved, and the retrieval precision can be remarkably improved in a mode of predetermining the geographic positions of the images to be searched; in addition, through correlating the image text features and the vector features of the original data and storing the image text features and the vector features in different storage positions, the simultaneous matching of the image text features and the vector features can be realized, the image retrieval precision is improved, and the retrieval speed is further improved; finally, the working efficiency can be remarkably improved by using the fasss similarity search tool to store data in the early stage and retrieve data in the later stage.
Drawings
FIG. 1 is a flow chart of a preferred embodiment of an image feature correlation processing method based on geospatial location partitioning in accordance with an embodiment of the present invention;
FIG. 2 is a logical relationship diagram of an image feature correlation processing system based on geospatial location partitioning in accordance with an embodiment of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of one or more embodiments. It may be evident, however, that such embodiment(s) may be practiced without these specific details.
Specific embodiments of the present application will be described in detail below with reference to the accompanying drawings.
Example 1
In order to illustrate the image feature association processing method based on the geospatial location division provided by the invention, fig. 1 shows a flow of the image feature association processing method based on the geospatial location division provided by the invention.
As shown in fig. 1, the image feature association processing method based on geospatial location division provided by the invention includes:
step S110: according to the geographic position of each path of video stream camera where the target image sample (namely the original data) is located, a first hash map table for storing vector features of the original data is built in a system memory.
Specifically, in order to facilitate distinguishing geographic sources of the target image samples, the total geographic space where all video stream cameras are located can be measured, and according to the geographic space position of each path of video stream camera, a unique cam id identifier is attached to the path of video stream camera so as to distinguish video stream cameras in different geographic space positions.
More specifically, in order to facilitate storage of original data and later image retrieval, the total geographic space where all video stream cameras are located may be clustered and divided according to the geographic space positions (i.e. longitude and latitude) of the video stream cameras, and the spatial space is divided into at least 5000 spatial regions (i.e. point location classifying spaces) according to the density of the video stream cameras in actual work, each spatial region includes a plurality of video stream camera point locations, and then a mapping relationship y=f (x) between the geographic position (i.e. longitude and latitude x) of each video stream camera and the point location classifying space (y) to which the video stream camera belongs is established; the mapping relation table is stored by establishing a corresponding first hash map table in a system memory, wherein keys of the first hash map table are numbers ID (y) of a point location classifying space (y), and values of the first hash map table are cam IDs and vector feature lists of all video stream cameras contained in the point location classifying space (y).
It should be noted that, the clustering is an existing region dividing technique, and the present invention mainly uses the clustering technique, so specific data processing procedures of the technique are not described herein.
Step S120: extracting image text characteristics and sample vector characteristics of a target image sample (original data), storing the image text characteristics and preset associated marker bits into a preset database, and storing the sample vector characteristics and the associated marker bits into the vector characteristic list; it should be noted that after the feature extraction is completed, each target image sample is given a unique association flag bit feature id identifier, so as to distinguish different target image samples, and in addition, the image text feature and the sample vector feature are associated through the association flag bit.
Specifically, in the process of extracting the image text features and the sample vector features of the target image samples (original data), the target image samples or the camera video streams where the target image samples or the camera video streams are located are directly input into a preset depth convolution neural network, the features of the targets (such as pedestrians and vehicles) in the target image samples or the camera video streams are extracted through the depth convolution neural network, the image text features and the vector features of the target image samples are finally obtained, the target image samples are endowed with a unique feature_id identifier, and the data association between the image text features and the sample vector features of the target image samples is realized through the feature_id identifier.
More specifically, the preset database storing the text features of the image and the associated flag bit feature_id can be a relational database so as to be used for searching the text features at a later stage; relational databases refer to the use of two-dimensional table models to store data, and a relational database is a data organization consisting of two-dimensional tables and associations between them. Of course, according to the characteristics of the text features, a non-relational database can be set and stored in key value pairs, the structure is not fixed, each tuple can have different fields, each tuple can be added with some own key value pairs according to the needs, the method is not limited to a fixed structure, and the time and space expenditure can be reduced. In practical use, a suitable database type can be reasonably selected according to the data structure.
It should be noted that, because the number of the original data (target image samples) is very large, the warehousing time is long, so that the warehousing of each original data is performed in a certain order, when the video stream cameras where the front and the rear two target image samples are located are identical, if two cam id identifiers are continuously established according to the two target image samples, the phenomenon of data matching confusion will occur in the later stage, in order to solve the problem, before the sample vector features and the associated flag bits are stored in the vector feature list,
firstly, determining a corresponding cam id identifier and a point location classification space according to the geographic position of the target image sample;
then judging whether the cam id identification and the number of the point location classification space are both existing in the first hash map table, if so, directly storing the sample vector features and associated marker bits of the target image sample into a vector feature list corresponding to the geographic position (corresponding to one cam id identification) of the target image sample;
otherwise, a new mapping relation is established according to the cam id identification corresponding to the target image sample and the number of the point location classification space, a new vector feature list is established according to the mapping relation, and the vector feature and the associated zone bit of the target image are stored in the new vector feature list.
Preferably, in consideration of the relation between the memory capacity occupation of the system and the data processing, in order to ensure that the whole system has higher data processing efficiency, after the sample vector features of each target image sample and the associated flag bits thereof are stored in the time length T of the vector feature list, whether the system memory exceeds a capacity threshold value or not can be judged, if so, the sample vector features and the associated flag bits thereof are stored in a second hash map table of a preset hard disk, and data in the corresponding vector feature list in the system memory is deleted. By the method, the transfer of the sample vector feature storage position can be realized, and the influence on the working efficiency caused by overlarge system memory occupation is avoided.
More preferably, in order to ensure the later retrieval speed of the sample vector feature transferred by the storage location, after deleting the data in the corresponding vector feature list in the system memory, the storage path of the sample vector feature stored in the preset hard disk is stored in the third hash map table, and the corresponding sample feature vector can be quickly found according to the storage path in the third hash map table during later deceleration; in addition, since the occupied space of the storage path of the feature vector is extremely small and can be ignored, the working efficiency of the system is not affected.
Step S130: and acquiring vector features and the affiliated geographical position of the target image to be searched, and searching the first hash map table according to the affiliated geographical position to acquire a vector feature list corresponding to the affiliated geographical position.
Specifically, the process of obtaining the vector features of the target image to be searched is the same as the process of obtaining the features of the sample target image, and is realized by performing feature extraction through a preset deep convolutional neural network, which is not described herein.
In the process of searching the first hash map table according to the affiliated geographic position to acquire a vector feature list corresponding to the affiliated geographic position, firstly determining the cam id identification of the video stream camera affiliated to the target image to be searched and the point position classifying space of the video stream camera affiliated to the target image to be searched, and then searching in the first hash map table according to the cam id identification and the number of the point position classifying space to find the corresponding vector feature list.
It should be noted that, for the original data, some sample target images of the existing video stream camera may not be obtained in the previous data storage, and in order to improve the coverage of the original data, the vector features of the target images to be searched that do not correspond to the cam id may be stored in the vector feature list.
Step S140: calculating the similarity between each sample vector feature in the vector feature list and the vector feature of the target image to be searched, and determining K sample vector features with the highest similarity and associated flag bits thereof; and then searching a preset database according to the K associated flag bits to obtain corresponding K image text features.
Specifically, in actual searching, classifying calculation is performed according to cam ID, corresponding ID (y) key values are mapped, if the ID (y) key values exist in the hash map, fass are called to perform similarity searching on a vector feature list of the ID (y) key values, and similarity and feature ID identifications of K most similar targets are obtained.
More specifically, calculating the similarity between each sample vector feature in the vector feature list and the vector feature of the target image to be searched by a fass similarity searching tool or other tools with similarity calculation, then sorting the vector features in the vector feature list according to the similarity, and finally obtaining K sample vector features with highest similarity and associated flag bits thereof; wherein, the value of K is 10 according to the actual requirement.
Through the step S140, K sample vector features and K image text features corresponding to the target image to be searched can be searched, and K sample target images with the highest similarity with the search target image can be found through data reduction and other modes according to the K sample vector features and the K image text features, so that the final purpose of searching the image by the image is achieved, and the working efficiency and the searching precision are remarkably improved.
Preferably, since the sample vector features of a part of the sample target image are stored in a preset hard disk, a second hash map table in the preset hard disk can be searched according to the affiliated geographic position to obtain a vector feature list corresponding to the affiliated geographic position;
calculating the similarity between each sample vector feature in the vector feature list and the vector feature of the target image to be searched, and determining K sample vector features with the highest similarity and associated flag bits thereof;
ordering the similarity of 2K sample vector features from the first hash map table and the second hash map table, and obtaining K sample vector features with highest similarity and associated flag bits thereof;
and searching the preset database according to the K associated flag bits to obtain corresponding K image text features.
It should be noted that, the search process of the second hash map table of the preset hard disk is the same as the search process of the second hash map table, and may be implemented by a fasss similarity search tool, which is not described herein again.
Furthermore, it should be further described that, regarding the geographic location of the target image to be searched (i.e., the geographic location of the video stream camera of the target image to be searched corresponds to the unique cam id identifier), because of the unknown origin of the target image to be searched, in most cases, the geographic location of the target image to be searched cannot be precisely determined, at this time, the geographic locations of all the video stream cameras in the source area may be determined according to the source area (or possible source area) of the target image to be searched, as the geographic locations of the target image to be searched, so as to form a cam id list, and then repeating steps S130 and S140 according to each cam id identifier of the cam id list in turn, so as to form multiple sets of feature sets (each feature set corresponds to K sample vector features and K image text features), and then obtain multiple sets (each set of K) of sample target images with the highest similarity of the target image to be searched. By the method, more effective sample target images can be obtained on the premise of ensuring the searching speed, and the working efficiency is further improved.
In the actual use process, if the established point-plane mapping relation and the searching speed and precision of the vector feature list do not reach the expected effect, the classification measurement can be carried out again according to the cam id identification of the original feature vector to obtain a new y=f (x) point-plane mapping relation, and a new hash map is established for storage. The vector feature list file block of the new ID (y) number corresponding item can be rewritten according to the index mode provided by faiss, such as inverted row, vector dimension reduction and the like, and the adaptation of the search speed and the search precision is carried out on the premise of adapting to the system software and hardware configuration, so that the corresponding search speed and precision are improved.
Example 2
Corresponding to the above method, the present application further provides an image feature association system based on geospatial location division, and fig. 2 shows a logical relationship of an image feature association processing system based on geospatial location division according to an embodiment of the present invention, as shown in fig. 2, where the system includes:
the system comprises a table construction unit, a first hash map table, a second hash map table and a storage unit, wherein the table construction unit is used for building a first hash map table in a system memory according to the geographic positions of all video stream cameras, and a vector feature list corresponding to each geographic position is arranged in the first hash map table;
the data storage unit is used for extracting image text characteristics and sample vector characteristics of a target image sample, storing the image text characteristics and preset associated marker bits into a preset database, and storing the sample vector characteristics and the associated marker bits into the vector characteristic list; wherein the image text feature is associated with the vector feature through the associated flag bit;
the vector feature list acquisition unit is used for acquiring vector features and the affiliated geographic position of the target image to be searched, and searching the first hash map table according to the affiliated geographic position to acquire a vector feature list corresponding to the affiliated geographic position;
the similarity matching unit is used for calculating the similarity between each sample vector feature in the vector feature list and the vector feature of the target image to be searched, and determining K sample vector features with the highest similarity and associated flag bits thereof;
and the searching unit is used for searching the preset database according to the K associated flag bits so as to acquire corresponding K image text features.
Wherein the table construction unit further comprises a space division unit and a mapping unit (not shown in the figure).
The space dividing unit is used for carrying out clustering division on the geographic space where the video stream camera is located so as to form a point location classifying space;
the mapping unit is used for establishing a first hash map table according to the mapping relation between the geographic position of each video stream camera and the point location classification space to which the video stream camera belongs; the keys of the first hash map table are numbers of the point location classification space, and the values of the first hash map table are vector feature lists of all video stream cameras contained in the point location classification space.
In another embodiment of the present invention, the data storage unit further comprises a point location determining unit and a number checking unit (not shown in the figure) for determining a storage manner of the sample vector features and the associated flag bits before storing the sample vector features and the associated flag bits in the vector feature list.
Specifically, the point location determining unit is used for determining a corresponding point location classification space according to the geographic position of the target image sample; the number checking unit is used for judging whether the number of the point position classifying space exists in the first hash map table or not; if the number of the point position classifying space exists, directly storing the sample vector characteristics and the associated marker bit of the target image sample into a vector characteristic list corresponding to the geographic position of the target image sample;
otherwise, a new vector feature list is established according to the number of the point location classification space corresponding to the target image sample, and the vector feature and the associated marker bit of the target image are stored in the new vector feature list.
In addition, the data storage unit may further include a table capacity monitoring unit (not shown in the figure), configured to determine whether the system memory exceeds a capacity threshold after a sample vector feature and an associated flag bit of each target image sample are stored in a T period of the vector feature list, and if so, store the sample vector feature and the associated flag bit thereof in a second hash map table of a preset hard disk, and delete data in a corresponding vector feature list in the system memory.
For the image feature associating system based on the geographic space position division, other specific embodiments corresponding to the image feature associating method based on the geographic space position division are similar to the implementation manner of the image feature associating method based on the geographic space position division, and are not described in detail herein.
As can be seen from the above embodiments, the image feature association processing method and system based on geospatial location division provided by the present invention has at least the following advantages:
1. by dividing the geographical position of the source of the picture and establishing a corresponding vector feature list, the classification and storage of the original data can be realized, the later retrieval speed can be improved, and the retrieval precision can be remarkably improved in a mode of predetermining the geographical position of the image to be searched;
2. through correlating the image text features and the vector features of the original data and storing the image text features and the vector features in different storage positions, the simultaneous matching of the image text features and the vector features can be realized, the image retrieval precision is improved, and the retrieval speed can be further improved.
3. The data storage and the data retrieval of the first hash map table, the second hash map table, the third hash map table and the preset database are realized through a fasss tool, so that the working efficiency of the system can be remarkably improved.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (10)
1. An image feature association processing method based on geospatial location division, which is characterized by comprising the following steps:
a first hash map table is established in a system memory according to the geographic position of each video stream camera, wherein a vector feature list corresponding to each geographic position is arranged in the first hash map table;
extracting image text features and sample vector features of a target image sample, storing the image text features and preset associated marker bits into a preset database, and storing the sample vector features and the associated marker bits into the vector feature list; wherein the image text feature is associated with the sample vector feature through the associated marker bit;
acquiring vector features and the affiliated geographical position of a target image to be searched, and searching the first hash map table according to the affiliated geographical position to acquire a vector feature list corresponding to the affiliated geographical position;
calculating the similarity between each sample vector feature in the vector feature list and the vector feature of the target image to be searched, and determining K sample vector features with the highest similarity and associated flag bits thereof;
searching a preset database according to the K associated marker bits with the highest similarity to obtain corresponding K image text features;
and according to the K sample vector features and the K image text features, finding K sample target images with highest similarity with the search target image.
2. The method for processing image feature association based on geospatial location partitioning according to claim 1, wherein the process of creating a first hash map table in system memory according to the geographic location of each video stream camera comprises:
clustering and dividing the geographic space where the video stream camera is located to form a point location classification space;
and establishing a first hash map table according to the mapping relation between the geographic position of each video stream camera and the point position classifying space to which the video stream camera belongs, wherein keys of the first hash map table are numbers of the point position classifying space, and the value of the first hash map table is a vector feature list of all video stream cameras contained in the point position classifying space.
3. The geospatial location division based image feature association processing method of claim 2 further comprising, prior to storing the sample vector features and the associated flag bits in the vector feature list:
determining a corresponding point location classification space according to the geographic position of the target image sample;
judging whether the number of the point position classifying space exists in the first hash map table, if so, directly storing the sample vector characteristics and the associated marker bits of the target image sample into a vector characteristic list corresponding to the geographic position of the target image sample;
otherwise, a new vector feature list is established according to the number of the point location classification space corresponding to the target image sample, and the vector feature and the associated marker bit of the target image are stored in the new vector feature list.
4. The method for image feature correlation processing based on geospatial location partitioning as recited in claim 3, wherein,
after the sample vector feature and the associated flag bit of each target image sample are stored in the T time length of the vector feature list, judging whether the system memory exceeds a capacity threshold, if so, storing the sample vector feature and the associated flag bit into a second hash map table of a preset hard disk, and deleting the data in the corresponding vector feature list in the system memory.
5. The image feature association processing method based on geospatial location division according to claim 4, wherein a third hash map table is further provided in the system memory; and, in addition, the processing unit,
after deleting the data in the corresponding vector feature list in the system memory, storing the storage path of the sample vector feature stored in the preset hard disk into the third hash map table.
6. The image feature association processing method based on geospatial location division according to claim 5, further comprising, after obtaining the vector feature and the geographic location of the target image to be searched:
searching a second hash map table in the preset hard disk according to the affiliated geographic position to acquire a vector feature list corresponding to the affiliated geographic position;
calculating the similarity between each sample vector feature in the vector feature list and the vector feature of the target image to be searched, and determining K sample vector features with the highest similarity and associated flag bits thereof;
ordering the similarity of 2K sample vector features from the first hash map table and the second hash map table, and obtaining K sample vector features with highest similarity and associated flag bits thereof;
and searching the preset database according to the K associated flag bits to obtain corresponding K image text features.
7. The image feature correlation processing method based on geospatial location division as claimed in any one of claims 5 or 6,
and the data storage and the data retrieval of the first hash map table, the second hash map table, the third hash map table and the preset database are realized through a fasss tool.
8. An image feature association processing system based on geospatial location partitioning, the system comprising:
the system comprises a table construction unit, a first hash map table, a second hash map table and a storage unit, wherein the table construction unit is used for building a first hash map table in a system memory according to the geographic positions of all video stream cameras, and a vector feature list corresponding to each geographic position is arranged in the first hash map table;
the data storage unit is used for extracting image text characteristics and sample vector characteristics of a target image sample, storing the image text characteristics and preset associated marker bits into a preset database, and storing the sample vector characteristics and the associated marker bits into the vector characteristic list; wherein the image text feature is associated with the vector feature through the associated flag bit;
the vector feature list acquisition unit is used for acquiring vector features and the affiliated geographic position of the target image to be searched, and searching the first hash map table according to the affiliated geographic position to acquire a vector feature list corresponding to the affiliated geographic position;
the similarity matching unit is used for calculating the similarity between each sample vector feature in the vector feature list and the vector feature of the target image to be searched, and determining K sample vector features with the highest similarity and associated flag bits thereof;
the searching unit is used for searching the preset database according to the K associated flag bits so as to obtain corresponding K image text features;
and the system finds K sample target images with highest similarity with the search target images according to the K sample vector features and the K image text features.
9. The geospatial location division based image feature associative processing system according to claim 8, wherein the table construction unit includes:
the space division unit is used for carrying out clustering division on the geographic space where the video stream camera is located so as to form a point location classification space;
the mapping unit is used for establishing a first hash map table according to the mapping relation between the geographic position of each video stream camera and the point position classifying space to which the video stream camera belongs, wherein the key of the first hash map table is the number of the point position classifying space, and the value of the first hash map table is the vector feature list of all the video stream cameras contained in the point position classifying space.
10. The geospatial location division based image feature associative processing system according to claim 9, wherein the data storage unit further comprises:
the point location determining unit is used for determining a corresponding point location classifying space according to the geographic position of the target image sample;
the number checking unit is used for judging whether the number of the point position classifying space exists in the first hash map table or not; wherein,,
if the target image sample exists, directly storing the sample vector characteristics and the associated marker bits of the target image sample into a vector characteristic list corresponding to the geographic position of the target image sample;
otherwise, a new vector feature list is established according to the number of the point location classification space corresponding to the target image sample, and the vector feature and the associated marker bit of the target image are stored in the new vector feature list.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010243925.4A CN111428063B (en) | 2020-03-31 | 2020-03-31 | Image feature association processing method and system based on geographic space position division |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010243925.4A CN111428063B (en) | 2020-03-31 | 2020-03-31 | Image feature association processing method and system based on geographic space position division |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111428063A CN111428063A (en) | 2020-07-17 |
| CN111428063B true CN111428063B (en) | 2023-06-30 |
Family
ID=71556177
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010243925.4A Active CN111428063B (en) | 2020-03-31 | 2020-03-31 | Image feature association processing method and system based on geographic space position division |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111428063B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112104730B (en) * | 2020-09-11 | 2023-03-28 | 杭州海康威视系统技术有限公司 | Scheduling method and device of storage tasks and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106776849A (en) * | 2016-11-28 | 2017-05-31 | 西安交通大学 | A kind of method and guide system to scheme quick-searching sight spot |
| CN109033308A (en) * | 2018-07-16 | 2018-12-18 | 安徽江淮汽车集团股份有限公司 | A kind of image search method and device |
| CN110019889A (en) * | 2017-12-01 | 2019-07-16 | 北京搜狗科技发展有限公司 | Training characteristics extract model and calculate the method and relevant apparatus of picture and query word relative coefficient |
| CN110069650A (en) * | 2017-10-10 | 2019-07-30 | 阿里巴巴集团控股有限公司 | A kind of searching method and processing equipment |
| CN110851629A (en) * | 2019-10-14 | 2020-02-28 | 信阳农林学院 | Image retrieval method |
-
2020
- 2020-03-31 CN CN202010243925.4A patent/CN111428063B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106776849A (en) * | 2016-11-28 | 2017-05-31 | 西安交通大学 | A kind of method and guide system to scheme quick-searching sight spot |
| CN110069650A (en) * | 2017-10-10 | 2019-07-30 | 阿里巴巴集团控股有限公司 | A kind of searching method and processing equipment |
| CN110019889A (en) * | 2017-12-01 | 2019-07-16 | 北京搜狗科技发展有限公司 | Training characteristics extract model and calculate the method and relevant apparatus of picture and query word relative coefficient |
| CN109033308A (en) * | 2018-07-16 | 2018-12-18 | 安徽江淮汽车集团股份有限公司 | A kind of image search method and device |
| CN110851629A (en) * | 2019-10-14 | 2020-02-28 | 信阳农林学院 | Image retrieval method |
Non-Patent Citations (1)
| Title |
|---|
| 叶巍 ; 龚建华 ; 郭娜 ; 路梅 ; 赵向军 ; .基于流形结构的图像地理信息标注方法.地理与地理信息科学.2015,(第03期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111428063A (en) | 2020-07-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4878178B2 (en) | Data processing method and apparatus, and processing program therefor | |
| CN107679078A (en) | A kind of bayonet socket image vehicle method for quickly retrieving and system based on deep learning | |
| CN109815993B (en) | GPS track-based regional feature extraction, database establishment and intersection identification method | |
| CN102254015A (en) | Image retrieval method based on visual phrases | |
| CN103617163B (en) | Quick target association method based on cluster analysis | |
| CN110569390B (en) | Efficient retrieval method for massive case data based on storage medium distinguishing | |
| CN106033443B (en) | A kind of expanding query method and device in vehicle retrieval | |
| CN106874421A (en) | Image search method based on self adaptation rectangular window | |
| CN110888880A (en) | Proximity analysis method, device, equipment and medium based on spatial index | |
| CN111583332B (en) | Visual positioning method, system and device based on parallel search 2D-3D matching | |
| CN110309810A (en) | A kind of pedestrian's recognition methods again based on batch center similarity | |
| CN111428063B (en) | Image feature association processing method and system based on geographic space position division | |
| CN112765120A (en) | Method for analyzing and extracting user movement track based on mobile phone signaling | |
| CN111582224A (en) | Face recognition system and method | |
| Kipf et al. | Approximate geospatial joins with precision guarantees | |
| CN106777350B (en) | Method and device for searching pictures with pictures based on bayonet data | |
| CN116721246B (en) | Continuous frame point cloud rapid labeling method and system | |
| CN112015937B (en) | Picture geographic positioning method and system | |
| Brakatsoulas et al. | Practical data management techniques for vehicle tracking data | |
| CN111325235B (en) | Multilingual-oriented universal place name semantic similarity calculation method and application thereof | |
| Le et al. | Improving logo spotting and matching for document categorization by a post-filter based on homography | |
| CN111061916B (en) | Video sharing system based on multi-target library image recognition | |
| CN106886783A (en) | A kind of image search method and system based on provincial characteristics | |
| CN106548118A (en) | The recognition and retrieval method and system of cinema projection content | |
| CN109408727B (en) | Intelligent user attention information recommendation method and system based on multidimensional perception data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |